Labeled Graph Generative Adversarial Networks
This work addresses the challenge of generating realistic labeled graphs for applications like citation networks and protein graphs, representing an incremental advancement in graph generative models.
The authors tackled the problem of generating labeled graph-structured data by proposing LGGAN, a generative adversarial network approach, and demonstrated that it outperforms alternative methods in generating diverse and structurally accurate graphs, as validated by improved performance in downstream graph classification tasks.
As a new approach to train generative models, \emph{generative adversarial networks} (GANs) have achieved considerable success in image generation. This framework has also recently been applied to data with graph structures. We propose labeled-graph generative adversarial networks (LGGAN) to train deep generative models for graph-structured data with node labels. We test the approach on various types of graph datasets, such as collections of citation networks and protein graphs. Experiment results show that our model can generate diverse labeled graphs that match the structural characteristics of the training data and outperforms all alternative approaches in quality and generality. To further evaluate the quality of the generated graphs, we use them on a downstream task of graph classification, and the results show that LGGAN can faithfully capture the important aspects of the graph structure.